Open Models Almanac
Methodsmodel architectureprediction head

single mention · model architecture

Diffusion decoding for vision-language-action policies

Identifies diffusion decoding in vision-language-action policies, but the supplied evidence does not specify its architecture.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See prediction head for the methods filed beside it.

Also called diffusion decoding.

Filed under model architecture › prediction head